Construction and Application of E-Government Simulation Network Experimental Teaching Practice Environment under the Background of Machine Learning

Abstract

With the rapid development of economy and Internet technology, e-government has been reflected in the reform of government information management and is closely related to the security of e-government networks. Existing technologies for evaluating network security can provide good evaluation results when dealing with deterministic data, but they are not sufficient to evaluate the uncertainty of information. In order to solve the problem of the construction and realization of the network training environment, a network security assessment method based on gray relational analysis and D-S theory proof is proposed. First, the scaling method is used to determine the weights of different levels of indicators, because different levels of indicators have different effects on the network state. Secondly, taking into account the differences in the degree of participation of different indicators at different levels, the participation function of each level indicator at the level is determined and a weighted amplitude coefficient to reduce the overall uncertainty is established. The network security situation is sudden and volatile. Therefore, the network security prediction method should have a good ability to deal with nonlinear problems. In this case, a network security state prediction method based on the GM performance model is proposed. The GM performance model has excellent nonlinear debugging functions. It has low requirements on the number of samples and good practicability. The experimental results show that the dynamic decision server push framework based on the XGBoost algorithm proposed in this paper has better performance than the single push method for push server, can use network resources appropriately, and improves the network environment security rate by at least 50%.